© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6296
    Prev
    Next
    INDEX
    Explanations

    phrases related to various significant or impactful occurrences

    oai_token-act-pair · gpt-3.5-turbo

    important social issues and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.88
    ADRA
    -0.75
    ãĥ¯ãĥ³
    -0.65
    azar
    -0.64
    avering
    -0.64
    odan
    -0.63
     Cosponsors
    -0.62
    IDA
    -0.61
    ¿½
    -0.60
    acan
    -0.59
    POSITIVE LOGITS
     nowadays
    1.51
     everywhere
    1.11
     amongst
    0.95
     lately
    0.93
     here
    0.90
     today
    0.90
     anymore
    0.89
     globally
    0.87
     among
    0.84
     worldwide
    0.84
    Activations Density 0.416%

    No Known Activations